ModelPlane
ModelPlane · One AI Gateway<br>Every model.<br>One endpoint.<br>Route across OpenAI, Anthropic, DeepSeek and more behind a single API. Model groups, fallback routing, and usage billing - built in.<br>Start free<br>No credit card · First 1M tokens free
example.py<br>from openai import OpenAI<br>client = OpenAI(<br>base_url="https://modelplane.dev/v1",<br>api_key="sk-mp-..."<br>resp = client.chat.completions.create(<br>model="prod-chat", # a model group<br>messages=[…]<br>→ routed to anthropic/claude, fell back OK
ONE API FOROpenAIAnthropicGeminiDeepSeekOpenRouterNovita AIMinimaxZ.AISee all →
Six primitives. One gateway.<br>Each works on its own. Together they replace the model-routing layer for every app you ship.
Model Groups<br>Package backends, models and routing policy behind one stable name your app calls directly.
Routing<br>Single-backend, weighted load-balancing, fallback, or conditional routing by request metadata.
Multiple Providers<br>OpenAI, Anthropic, DeepSeek, OpenRouter and any custom OpenAI-compatible service.
Coding Plans<br>Run coding-plan backends beside credit-based keys, with quota and balance visibility.
Thinking Output<br>One reasoning request format; read standardized reasoning text across every model.
Usage & Billing<br>Track spend and tokens per group, key and customer tier in a single console.
Failover before your users notice.<br>Define a policy once. The gateway evaluates weights, retries, and fallbacks on every request — and hands back a standardized response no matter which backend answered.<br>WeightedFallbackConditionalSingle-backend
routing · prod-chat<br>→ POST /v1/chat/completions model: "prod-chat"<br>✓ matched group · policy: weighted + fallback<br>→ openai/gpt-4o weight 70% 504 timeout<br>→ anthropic/claude-3.7 fallback 200 · 240ms<br>← response streamed from anthropic/claude-3.7
Pay for credits, not seats.<br>All plans draw credit at the same $0.02 / 1M-token rate.
Compare all plans<br>FreeCURRENT<br>$0/mo<br>$1 in credit to start · 1 active key · $0.02 / 1M tok
StartupPOPULAR<br>$20/mo<br>$20 credit included monthly · 10 active keys · $0.02 / 1M tok
Start shipping.<br>One endpoint for every model. Free for the first 1M tokens — no credit card required.<br>Start free<br>OpenAI-compatible 8 providers No lock-in